/**
* Main loop for OUTRES
*
* @param relation Relation to process
* @return Outlier detection result
*/
public OutlierResult run(Relation<V> relation) {
WritableDoubleDataStore ranks =
DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
DoubleMinMax minmax = new DoubleMinMax();
KernelDensityEstimator kernel = new KernelDensityEstimator(relation);
long[] subspace = BitsUtil.zero(kernel.dim);
FiniteProgress progress =
LOG.isVerbose() ? new FiniteProgress("OUTRES scores", relation.size(), LOG) : null;
for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
BitsUtil.zeroI(subspace);
double score = outresScore(0, subspace, iditer, kernel);
ranks.putDouble(iditer, score);
minmax.put(score);
LOG.incrementProcessed(progress);
}
LOG.ensureCompleted(progress);
OutlierScoreMeta meta =
new InvertedOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0., 1., 1.);
OutlierResult outresResult =
new OutlierResult(
meta,
new MaterializedDoubleRelation("OUTRES", "outres-score", ranks, relation.getDBIDs()));
return outresResult;
}
/**
* Run the Eclat algorithm
*
* @param db Database to process
* @param relation Bit vector relation
* @return Frequent patterns found
*/
public FrequentItemsetsResult run(Database db, final Relation<BitVector> relation) {
// TODO: implement with resizable arrays, to not need dim.
final int dim = RelationUtil.dimensionality(relation);
final VectorFieldTypeInformation<BitVector> meta = RelationUtil.assumeVectorField(relation);
// Compute absolute minsupport
final int minsupp = getMinimumSupport(relation.size());
LOG.verbose("Build 1-dimensional transaction lists.");
Duration ctime = LOG.newDuration(STAT + "eclat.transposition.time").begin();
DBIDs[] idx = buildIndex(relation, dim, minsupp);
LOG.statistics(ctime.end());
FiniteProgress prog =
LOG.isVerbose() ? new FiniteProgress("Building frequent itemsets", idx.length, LOG) : null;
Duration etime = LOG.newDuration(STAT + "eclat.extraction.time").begin();
final List<Itemset> solution = new ArrayList<>();
for (int i = 0; i < idx.length; i++) {
LOG.incrementProcessed(prog);
extractItemsets(idx, i, minsupp, solution);
}
LOG.ensureCompleted(prog);
Collections.sort(solution);
LOG.statistics(etime.end());
LOG.statistics(new LongStatistic(STAT + "frequent-itemsets", solution.size()));
return new FrequentItemsetsResult("Eclat", "eclat", solution, meta);
}
@Override
public void run() {
Database database = input.getDatabase();
Relation<O> relation = database.getRelation(distance.getInputTypeRestriction());
DistanceQuery<O> distanceQuery = database.getDistanceQuery(relation, distance);
KNNQuery<O> knnQ = database.getKNNQuery(distanceQuery, DatabaseQuery.HINT_HEAVY_USE);
// open file.
try (RandomAccessFile file = new RandomAccessFile(out, "rw");
FileChannel channel = file.getChannel();
// and acquire a file write lock
FileLock lock = channel.lock()) {
// write magic header
file.writeInt(KNN_CACHE_MAGIC);
int bufsize = k * 12 * 2 + 10; // Initial size, enough for 2 kNN.
ByteBuffer buffer = ByteBuffer.allocateDirect(bufsize);
FiniteProgress prog =
LOG.isVerbose() ? new FiniteProgress("Computing kNN", relation.size(), LOG) : null;
for (DBIDIter it = relation.iterDBIDs(); it.valid(); it.advance()) {
final KNNList nn = knnQ.getKNNForDBID(it, k);
final int nnsize = nn.size();
// Grow the buffer when needed:
if (nnsize * 12 + 10 > bufsize) {
while (nnsize * 12 + 10 > bufsize) {
bufsize <<= 1;
}
buffer = ByteBuffer.allocateDirect(bufsize);
}
buffer.clear();
ByteArrayUtil.writeUnsignedVarint(buffer, it.internalGetIndex());
ByteArrayUtil.writeUnsignedVarint(buffer, nnsize);
int c = 0;
for (DoubleDBIDListIter ni = nn.iter(); ni.valid(); ni.advance(), c++) {
ByteArrayUtil.writeUnsignedVarint(buffer, ni.internalGetIndex());
buffer.putDouble(ni.doubleValue());
}
if (c != nn.size()) {
throw new AbortException("Sizes did not agree. Cache is invalid.");
}
buffer.flip();
channel.write(buffer);
LOG.incrementProcessed(prog);
}
LOG.ensureCompleted(prog);
lock.release();
} catch (IOException e) {
LOG.exception(e);
}
// FIXME: close!
}
@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
if (relation.size() <= 0) {
return new Clustering<>("k-Means Clustering", "kmeans-clustering");
}
// Choose initial means
if (LOG.isStatistics()) {
LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
}
double[][] means = initializer.chooseInitialMeans(database, relation, k, getDistanceFunction());
// Setup cluster assignment store
List<ModifiableDBIDs> clusters = new ArrayList<>();
for (int i = 0; i < k; i++) {
clusters.add(DBIDUtil.newHashSet((int) (relation.size() * 2. / k)));
}
WritableIntegerDataStore assignment =
DataStoreUtil.makeIntegerStorage(
relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
double[] varsum = new double[k];
IndefiniteProgress prog =
LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
DoubleStatistic varstat =
LOG.isStatistics()
? new DoubleStatistic(this.getClass().getName() + ".variance-sum")
: null;
int iteration = 0;
for (; maxiter <= 0 || iteration < maxiter; iteration++) {
LOG.incrementProcessed(prog);
boolean changed = assignToNearestCluster(relation, means, clusters, assignment, varsum);
logVarstat(varstat, varsum);
// Stop if no cluster assignment changed.
if (!changed) {
break;
}
// Recompute means.
means = means(clusters, means, relation);
}
LOG.setCompleted(prog);
if (LOG.isStatistics()) {
LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
}
// Wrap result
Clustering<KMeansModel> result = new Clustering<>("k-Means Clustering", "kmeans-clustering");
for (int i = 0; i < clusters.size(); i++) {
DBIDs ids = clusters.get(i);
if (ids.size() == 0) {
continue;
}
KMeansModel model = new KMeansModel(means[i], varsum[i]);
result.addToplevelCluster(new Cluster<>(ids, model));
}
return result;
}
@Override
public Clustering<BiclusterWithInversionsModel> biclustering() {
double[][] mat = RelationUtil.relationAsMatrix(relation, rowIDs);
BiclusterCandidate cand = new BiclusterCandidate(getRowDim(), getColDim());
Clustering<BiclusterWithInversionsModel> result =
new Clustering<>("Cheng-and-Church", "Cheng and Church Biclustering");
ModifiableDBIDs noise = DBIDUtil.newHashSet(relation.getDBIDs());
FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Extracting Cluster", n, LOG) : null;
for (int i = 0; i < n; i++) {
cand.reset();
multipleNodeDeletion(mat, cand);
if (LOG.isVeryVerbose()) {
LOG.veryverbose(
"Residue after Alg 2: " + cand.residue + " " + cand.rowcard + "x" + cand.colcard);
}
singleNodeDeletion(mat, cand);
if (LOG.isVeryVerbose()) {
LOG.veryverbose(
"Residue after Alg 1: " + cand.residue + " " + cand.rowcard + "x" + cand.colcard);
}
nodeAddition(mat, cand);
if (LOG.isVeryVerbose()) {
LOG.veryverbose(
"Residue after Alg 3: " + cand.residue + " " + cand.rowcard + "x" + cand.colcard);
}
cand.maskMatrix(mat, dist);
BiclusterWithInversionsModel model =
new BiclusterWithInversionsModel(colsBitsetToIDs(cand.cols), rowsBitsetToIDs(cand.irow));
final ArrayDBIDs cids = rowsBitsetToIDs(cand.rows);
noise.removeDBIDs(cids);
result.addToplevelCluster(new Cluster<>(cids, model));
if (LOG.isVerbose()) {
LOG.verbose("Score of bicluster " + (i + 1) + ": " + cand.residue + "\n");
LOG.verbose("Number of rows: " + cand.rowcard + "\n");
LOG.verbose("Number of columns: " + cand.colcard + "\n");
// LOG.verbose("Total number of masked values: " + maskedVals.size() +
// "\n");
}
LOG.incrementProcessed(prog);
}
// Add a noise cluster, full-dimensional.
if (!noise.isEmpty()) {
long[] allcols = BitsUtil.ones(getColDim());
BiclusterWithInversionsModel model =
new BiclusterWithInversionsModel(colsBitsetToIDs(allcols), DBIDUtil.EMPTYDBIDS);
result.addToplevelCluster(new Cluster<>(noise, true, model));
}
LOG.ensureCompleted(prog);
return result;
}
/**
* Preprocessing step: determine the radii of interest for each point.
*
* @param ids IDs to process
* @param rangeQuery Range query
* @param interestingDistances Distances of interest
*/
protected void precomputeInterestingRadii(
DBIDs ids,
RangeQuery<O> rangeQuery,
WritableDataStore<DoubleIntArrayList> interestingDistances) {
FiniteProgress progressPreproc =
LOG.isVerbose() ? new FiniteProgress("LOCI preprocessing", ids.size(), LOG) : null;
for (DBIDIter iditer = ids.iter(); iditer.valid(); iditer.advance()) {
DoubleDBIDList neighbors = rangeQuery.getRangeForDBID(iditer, rmax);
// build list of critical distances
DoubleIntArrayList cdist = new DoubleIntArrayList(neighbors.size() << 1);
{
int i = 0;
DoubleDBIDListIter ni = neighbors.iter();
while (ni.valid()) {
final double curdist = ni.doubleValue();
++i;
ni.advance();
// Skip, if tied to the next object:
if (ni.valid() && curdist == ni.doubleValue()) {
continue;
}
cdist.append(curdist, i);
// Scale radius, and reinsert
if (alpha != 1.) {
final double ri = curdist / alpha;
if (ri <= rmax) {
cdist.append(ri, Integer.MIN_VALUE);
}
}
}
}
cdist.sort();
// fill the gaps to have fast lookups of number of neighbors at a given
// distance.
int lastk = 0;
for (int i = 0, size = cdist.size(); i < size; i++) {
final int k = cdist.getInt(i);
if (k == Integer.MIN_VALUE) {
cdist.setValue(i, lastk);
} else {
lastk = k;
}
}
// TODO: shrink the list, removing duplicate radii?
interestingDistances.put(iditer, cdist);
LOG.incrementProcessed(progressPreproc);
}
LOG.ensureCompleted(progressPreproc);
}
/**
* Process a database
*
* @param database Database to process
* @param relation Relation to process
* @return Histogram of ranking qualities
*/
public HistogramResult<DoubleVector> run(Database database, Relation<O> relation) {
final DistanceQuery<O> distanceQuery =
database.getDistanceQuery(relation, getDistanceFunction());
final KNNQuery<O> knnQuery = database.getKNNQuery(distanceQuery, relation.size());
if (LOG.isVerbose()) {
LOG.verbose("Preprocessing clusters...");
}
// Cluster by labels
Collection<Cluster<Model>> split =
(new ByLabelOrAllInOneClustering()).run(database).getAllClusters();
DoubleStaticHistogram hist = new DoubleStaticHistogram(numbins, 0.0, 1.0);
if (LOG.isVerbose()) {
LOG.verbose("Processing points...");
}
FiniteProgress progress =
LOG.isVerbose()
? new FiniteProgress("Computing ROC AUC values", relation.size(), LOG)
: null;
MeanVariance mv = new MeanVariance();
// sort neighbors
for (Cluster<?> clus : split) {
for (DBIDIter iter = clus.getIDs().iter(); iter.valid(); iter.advance()) {
KNNList knn = knnQuery.getKNNForDBID(iter, relation.size());
double result = new ROCEvaluation().evaluate(clus, knn);
mv.put(result);
hist.increment(result, 1. / relation.size());
LOG.incrementProcessed(progress);
}
}
LOG.ensureCompleted(progress);
// Transform Histogram into a Double Vector array.
Collection<DoubleVector> res = new ArrayList<>(relation.size());
for (DoubleStaticHistogram.Iter iter = hist.iter(); iter.valid(); iter.advance()) {
DoubleVector row = new DoubleVector(new double[] {iter.getCenter(), iter.getValue()});
res.add(row);
}
HistogramResult<DoubleVector> result =
new HistogramResult<>("Ranking Quality Histogram", "ranking-histogram", res);
result.addHeader("Mean: " + mv.getMean() + " Variance: " + mv.getSampleVariance());
return result;
}
public Result run(Database database, Relation<O> rel) {
DistanceQuery<O> dq = rel.getDistanceQuery(getDistanceFunction());
int size = rel.size();
long pairs = (size * (long) size) >> 1;
final long ssize = sampling <= 1 ? (long) Math.ceil(sampling * pairs) : (long) sampling;
if (ssize > Integer.MAX_VALUE) {
throw new AbortException("Sampling size too large.");
}
final int qsize = quantile <= 0 ? 1 : (int) Math.ceil(quantile * ssize);
DoubleMaxHeap heap = new DoubleMaxHeap(qsize);
ArrayDBIDs ids = DBIDUtil.ensureArray(rel.getDBIDs());
DBIDArrayIter i1 = ids.iter(), i2 = ids.iter();
Random r = rand.getSingleThreadedRandom();
FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Sampling", (int) ssize, LOG) : null;
for (long i = 0; i < ssize; i++) {
int x = r.nextInt(size - 1) + 1, y = r.nextInt(x);
double dist = dq.distance(i1.seek(x), i2.seek(y));
// Skip NaN, and/or zeros.
if (dist != dist || (nozeros && dist < Double.MIN_NORMAL)) {
continue;
}
heap.add(dist, qsize);
LOG.incrementProcessed(prog);
}
LOG.statistics(new DoubleStatistic(PREFIX + ".quantile", quantile));
LOG.statistics(new LongStatistic(PREFIX + ".samplesize", ssize));
LOG.statistics(new DoubleStatistic(PREFIX + ".distance", heap.peek()));
LOG.ensureCompleted(prog);
Collection<String> header = Arrays.asList(new String[] {"Distance"});
Collection<Vector> data = Arrays.asList(new Vector[] {new Vector(heap.peek())});
return new CollectionResult<Vector>("Distances sample", "distance-sample", data, header);
}
/**
* Run the algorithm
*
* @param database Database to process
* @param relation Relation to process
* @return Outlier result
*/
public OutlierResult run(Database database, Relation<O> relation) {
DistanceQuery<O> distFunc = database.getDistanceQuery(relation, getDistanceFunction());
RangeQuery<O> rangeQuery = database.getRangeQuery(distFunc);
DBIDs ids = relation.getDBIDs();
// LOCI preprocessing step
WritableDataStore<DoubleIntArrayList> interestingDistances =
DataStoreUtil.makeStorage(
relation.getDBIDs(),
DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_SORTED,
DoubleIntArrayList.class);
precomputeInterestingRadii(ids, rangeQuery, interestingDistances);
// LOCI main step
FiniteProgress progressLOCI =
LOG.isVerbose() ? new FiniteProgress("LOCI scores", relation.size(), LOG) : null;
WritableDoubleDataStore mdef_norm =
DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
WritableDoubleDataStore mdef_radius =
DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
DoubleMinMax minmax = new DoubleMinMax();
// Shared instance, to save allocations.
MeanVariance mv_n_r_alpha = new MeanVariance();
for (DBIDIter iditer = ids.iter(); iditer.valid(); iditer.advance()) {
final DoubleIntArrayList cdist = interestingDistances.get(iditer);
final double maxdist = cdist.getDouble(cdist.size() - 1);
final int maxneig = cdist.getInt(cdist.size() - 1);
double maxmdefnorm = 0.0;
double maxnormr = 0;
if (maxneig >= nmin) {
// Compute the largest neighborhood we will need.
DoubleDBIDList maxneighbors = rangeQuery.getRangeForDBID(iditer, maxdist);
// TODO: Ensure the result is sorted. This is currently implied.
// For any critical distance, compute the normalized MDEF score.
for (int i = 0, size = cdist.size(); i < size; i++) {
// Only start when minimum size is fulfilled
if (cdist.getInt(i) < nmin) {
continue;
}
final double r = cdist.getDouble(i);
final double alpha_r = alpha * r;
// compute n(p_i, \alpha * r) from list (note: alpha_r is not cdist!)
final int n_alphar = cdist.getInt(cdist.find(alpha_r));
// compute \hat{n}(p_i, r, \alpha) and the corresponding \simga_{MDEF}
mv_n_r_alpha.reset();
for (DoubleDBIDListIter neighbor = maxneighbors.iter();
neighbor.valid();
neighbor.advance()) {
// Stop at radius r
if (neighbor.doubleValue() > r) {
break;
}
DoubleIntArrayList cdist2 = interestingDistances.get(neighbor);
int rn_alphar = cdist2.getInt(cdist2.find(alpha_r));
mv_n_r_alpha.put(rn_alphar);
}
// We only use the average and standard deviation
final double nhat_r_alpha = mv_n_r_alpha.getMean();
final double sigma_nhat_r_alpha = mv_n_r_alpha.getNaiveStddev();
// Redundant divisions by nhat_r_alpha removed.
final double mdef = nhat_r_alpha - n_alphar;
final double sigmamdef = sigma_nhat_r_alpha;
final double mdefnorm = mdef / sigmamdef;
if (mdefnorm > maxmdefnorm) {
maxmdefnorm = mdefnorm;
maxnormr = r;
}
}
} else {
// FIXME: when nmin was not fulfilled - what is the proper value then?
maxmdefnorm = Double.POSITIVE_INFINITY;
maxnormr = maxdist;
}
mdef_norm.putDouble(iditer, maxmdefnorm);
mdef_radius.putDouble(iditer, maxnormr);
minmax.put(maxmdefnorm);
LOG.incrementProcessed(progressLOCI);
}
LOG.ensureCompleted(progressLOCI);
DoubleRelation scoreResult =
new MaterializedDoubleRelation(
"LOCI normalized MDEF", "loci-mdef-outlier", mdef_norm, relation.getDBIDs());
OutlierScoreMeta scoreMeta =
new QuotientOutlierScoreMeta(
minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 0.0);
OutlierResult result = new OutlierResult(scoreMeta, scoreResult);
result.addChildResult(
new MaterializedDoubleRelation(
"LOCI MDEF Radius", "loci-critical-radius", mdef_radius, relation.getDBIDs()));
return result;
}
/**
* Run the algorithm
*
* @param db Database
* @param relation Relation
* @return Clustering hierarchy
*/
public PointerHierarchyRepresentationResult run(Database db, Relation<O> relation) {
DistanceQuery<O> dq = db.getDistanceQuery(relation, getDistanceFunction());
ArrayDBIDs ids = DBIDUtil.ensureArray(relation.getDBIDs());
final int size = ids.size();
if (size > 0x10000) {
throw new AbortException(
"This implementation does not scale to data sets larger than "
+ 0x10000
+ " instances (~17 GB RAM), which results in an integer overflow.");
}
if (Linkage.SINGLE.equals(linkage)) {
LOG.verbose("Notice: SLINK is a much faster algorithm for single-linkage clustering!");
}
// Compute the initial (lower triangular) distance matrix.
double[] scratch = new double[triangleSize(size)];
DBIDArrayIter ix = ids.iter(), iy = ids.iter(), ij = ids.iter();
// Position counter - must agree with computeOffset!
int pos = 0;
boolean square =
Linkage.WARD.equals(linkage)
&& !(SquaredEuclideanDistanceFunction.class.isInstance(getDistanceFunction()));
for (int x = 0; ix.valid(); x++, ix.advance()) {
iy.seek(0);
for (int y = 0; y < x; y++, iy.advance()) {
scratch[pos] = dq.distance(ix, iy);
// Ward uses variances -- i.e. squared values
if (square) {
scratch[pos] *= scratch[pos];
}
pos++;
}
}
// Initialize space for result:
WritableDBIDDataStore parent =
DataStoreUtil.makeDBIDStorage(
ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC);
WritableDoubleDataStore height =
DataStoreUtil.makeDoubleStorage(
ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC);
WritableIntegerDataStore csize =
DataStoreUtil.makeIntegerStorage(
ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
parent.put(it, it);
height.put(it, Double.POSITIVE_INFINITY);
csize.put(it, 1);
}
// Repeat until everything merged, except the desired number of clusters:
FiniteProgress prog =
LOG.isVerbose() ? new FiniteProgress("Agglomerative clustering", size - 1, LOG) : null;
for (int i = 1; i < size; i++) {
double min = Double.POSITIVE_INFINITY;
int minx = -1, miny = -1;
for (ix.seek(0); ix.valid(); ix.advance()) {
if (height.doubleValue(ix) < Double.POSITIVE_INFINITY) {
continue;
}
final int xbase = triangleSize(ix.getOffset());
for (iy.seek(0); iy.getOffset() < ix.getOffset(); iy.advance()) {
if (height.doubleValue(iy) < Double.POSITIVE_INFINITY) {
continue;
}
final int idx = xbase + iy.getOffset();
if (scratch[idx] <= min) {
min = scratch[idx];
minx = ix.getOffset();
miny = iy.getOffset();
}
}
}
assert (minx >= 0 && miny >= 0);
// Avoid allocating memory, by reusing existing iterators:
ix.seek(minx);
iy.seek(miny);
// Perform merge in data structure: x -> y
// Since y < x, prefer keeping y, dropping x.
int sizex = csize.intValue(ix), sizey = csize.intValue(iy);
height.put(ix, min);
parent.put(ix, iy);
csize.put(iy, sizex + sizey);
// Update distance matrix. Note: miny < minx
final int xbase = triangleSize(minx), ybase = triangleSize(miny);
// Write to (y, j), with j < y
for (ij.seek(0); ij.getOffset() < miny; ij.advance()) {
if (height.doubleValue(ij) < Double.POSITIVE_INFINITY) {
continue;
}
final int sizej = csize.intValue(ij);
scratch[ybase + ij.getOffset()] =
linkage.combine(
sizex,
scratch[xbase + ij.getOffset()],
sizey,
scratch[ybase + ij.getOffset()],
sizej,
min);
}
// Write to (j, y), with y < j < x
for (ij.seek(miny + 1); ij.getOffset() < minx; ij.advance()) {
if (height.doubleValue(ij) < Double.POSITIVE_INFINITY) {
continue;
}
final int jbase = triangleSize(ij.getOffset());
final int sizej = csize.intValue(ij);
scratch[jbase + miny] =
linkage.combine(
sizex, scratch[xbase + ij.getOffset()], sizey, scratch[jbase + miny], sizej, min);
}
// Write to (j, y), with y < x < j
for (ij.seek(minx + 1); ij.valid(); ij.advance()) {
if (height.doubleValue(ij) < Double.POSITIVE_INFINITY) {
continue;
}
final int jbase = triangleSize(ij.getOffset());
final int sizej = csize.intValue(ij);
scratch[jbase + miny] =
linkage.combine(sizex, scratch[jbase + minx], sizey, scratch[jbase + miny], sizej, min);
}
LOG.incrementProcessed(prog);
}
LOG.ensureCompleted(prog);
return new PointerHierarchyRepresentationResult(ids, parent, height);
}
@Override
public void parse(InputStream in, DistanceCacheWriter cache) {
reader.reset(in);
int min = Integer.MAX_VALUE, max = Integer.MIN_VALUE;
IndefiniteProgress prog =
LOG.isVerbose() ? new IndefiniteProgress("Parsing distance matrix", LOG) : null;
try {
while (reader.nextLineExceptComments()) {
LOG.incrementProcessed(prog);
if (!tokenizer.valid()) {
throw new IllegalArgumentException(
"Less than three values in line " + reader.getLineNumber());
}
int id1, id2;
try {
id1 = (int) tokenizer.getLongBase10();
tokenizer.advance();
} catch (NumberFormatException e) {
throw new IllegalArgumentException(
"Error in line " + reader.getLineNumber() + ": id1 is not an integer!");
}
if (!tokenizer.valid()) {
throw new IllegalArgumentException(
"Less than three values in line " + reader.getLineNumber());
}
try {
id2 = (int) tokenizer.getLongBase10();
tokenizer.advance();
} catch (NumberFormatException e) {
throw new IllegalArgumentException(
"Error in line " + reader.getLineNumber() + ": id2 is not an integer!");
}
if (!tokenizer.valid()) {
throw new IllegalArgumentException(
"Less than three values in line " + reader.getLineNumber());
}
// Track minimum and maximum
if (id1 < id2) {
min = (id1 < min) ? id1 : min;
max = (id2 > min) ? id2 : max;
} else {
min = (id2 < min) ? id2 : min;
max = (id1 > min) ? id1 : max;
}
try {
double distance = tokenizer.getDouble();
cache.put(id1, id2, distance);
} catch (IllegalArgumentException e) {
throw new IllegalArgumentException(
"Error in line " + reader.getLineNumber() + ":" + e.getMessage(), e);
}
tokenizer.advance();
if (tokenizer.valid()) {
throw new IllegalArgumentException(
"More than three values in line " + reader.getLineNumber());
}
}
} catch (IOException e) {
throw new IllegalArgumentException(
"Error while parsing line " + reader.getLineNumber() + ".");
}
LOG.setCompleted(prog);
// check if all distance values are specified
for (int i1 = min; i1 <= max; i1++) {
for (int i2 = i1 + 1; i2 <= max; i2++) {
if (!cache.containsKey(i1, i2)) {
throw new IllegalArgumentException(
"Distance value for " + i1 + " to " + i2 + " is missing!");
}
}
}
}
/**
* Performs a single run of FastDOC, finding a single cluster.
*
* @param database Database context
* @param relation used to get actual values for DBIDs.
* @param S The set of points we're working on.
* @param d Dimensionality of the data set we're currently working on.
* @param r Size of random samples.
* @param m Number of inner iterations (per seed point).
* @param n Number of outer iterations (seed points).
* @return a cluster, if one is found, else <code>null</code>.
*/
private Cluster<SubspaceModel> runFastDOC(
Database database, Relation<V> relation, ArrayModifiableDBIDs S, int d, int n, int m, int r) {
// Relevant attributes of highest cardinality.
long[] D = null;
// The seed point for the best dimensions.
DBIDVar dV = DBIDUtil.newVar();
// Inform the user about the progress in the current iteration.
FiniteProgress iprogress =
LOG.isVerbose()
? new FiniteProgress("Iteration progress for current cluster", m * n, LOG)
: null;
Random random = rnd.getSingleThreadedRandom();
DBIDArrayIter iter = S.iter();
outer:
for (int i = 0; i < n; ++i) {
// Pick a random seed point.
iter.seek(random.nextInt(S.size()));
for (int j = 0; j < m; ++j) {
// Choose a set of random points.
DBIDs randomSet = DBIDUtil.randomSample(S, r, random);
// Initialize cluster info.
long[] nD = BitsUtil.zero(d);
// Test each dimension.
for (int k = 0; k < d; ++k) {
if (dimensionIsRelevant(k, relation, randomSet)) {
BitsUtil.setI(nD, k);
}
}
if (D == null || BitsUtil.cardinality(nD) > BitsUtil.cardinality(D)) {
D = nD;
dV.set(iter);
if (BitsUtil.cardinality(D) >= d_zero) {
if (iprogress != null) {
iprogress.setProcessed(iprogress.getTotal(), LOG);
}
break outer;
}
}
LOG.incrementProcessed(iprogress);
}
}
LOG.ensureCompleted(iprogress);
// If no relevant dimensions were found, skip it.
if (D == null || BitsUtil.cardinality(D) == 0) {
return null;
}
// Get all points in the box.
SubspaceMaximumDistanceFunction df = new SubspaceMaximumDistanceFunction(D);
DistanceQuery<V> dq = database.getDistanceQuery(relation, df);
RangeQuery<V> rq = database.getRangeQuery(dq, DatabaseQuery.HINT_SINGLE);
// TODO: add filtering capabilities into query API!
DBIDs C = DBIDUtil.intersection(S, rq.getRangeForDBID(dV, w));
// If we have a non-empty cluster, return it.
return (C.size() > 0) ? makeCluster(relation, C, D) : null;
}
/**
* Performs a single run of DOC, finding a single cluster.
*
* @param database Database context
* @param relation used to get actual values for DBIDs.
* @param S The set of points we're working on.
* @param d Dimensionality of the data set we're currently working on.
* @param r Size of random samples.
* @param m Number of inner iterations (per seed point).
* @param n Number of outer iterations (seed points).
* @param minClusterSize Minimum size a cluster must have to be accepted.
* @return a cluster, if one is found, else <code>null</code>.
*/
private Cluster<SubspaceModel> runDOC(
Database database,
Relation<V> relation,
ArrayModifiableDBIDs S,
final int d,
int n,
int m,
int r,
int minClusterSize) {
// Best cluster for the current run.
DBIDs C = null;
// Relevant attributes for the best cluster.
long[] D = null;
// Quality of the best cluster.
double quality = Double.NEGATIVE_INFINITY;
// Bounds for our cluster.
// ModifiableHyperBoundingBox bounds = new ModifiableHyperBoundingBox(new
// double[d], new double[d]);
// Weights for distance (= rectangle query)
SubspaceMaximumDistanceFunction df = new SubspaceMaximumDistanceFunction(BitsUtil.zero(d));
DistanceQuery<V> dq = database.getDistanceQuery(relation, df);
RangeQuery<V> rq = database.getRangeQuery(dq);
// Inform the user about the progress in the current iteration.
FiniteProgress iprogress =
LOG.isVerbose()
? new FiniteProgress("Iteration progress for current cluster", m * n, LOG)
: null;
Random random = rnd.getSingleThreadedRandom();
DBIDArrayIter iter = S.iter();
for (int i = 0; i < n; ++i) {
// Pick a random seed point.
iter.seek(random.nextInt(S.size()));
for (int j = 0; j < m; ++j) {
// Choose a set of random points.
DBIDs randomSet = DBIDUtil.randomSample(S, r, random);
// Initialize cluster info.
long[] nD = BitsUtil.zero(d);
// Test each dimension and build bounding box.
for (int k = 0; k < d; ++k) {
if (dimensionIsRelevant(k, relation, randomSet)) {
BitsUtil.setI(nD, k);
}
}
if (BitsUtil.cardinality(nD) > 0) {
// Get all points in the box.
df.setSelectedDimensions(nD);
// TODO: add filtering capabilities into query API!
DBIDs nC = DBIDUtil.intersection(S, rq.getRangeForDBID(iter, w));
if (LOG.isDebuggingFiner()) {
LOG.finer(
"Testing a cluster candidate, |C| = "
+ nC.size()
+ ", |D| = "
+ BitsUtil.cardinality(nD));
}
// Is the cluster large enough?
if (nC.size() < minClusterSize) {
// Too small.
if (LOG.isDebuggingFiner()) {
LOG.finer("... but it's too small.");
}
} else {
// Better cluster than before?
double nQuality = computeClusterQuality(nC.size(), BitsUtil.cardinality(nD));
if (nQuality > quality) {
if (LOG.isDebuggingFiner()) {
LOG.finer("... and it's the best so far: " + nQuality + " vs. " + quality);
}
C = nC;
D = nD;
quality = nQuality;
} else {
if (LOG.isDebuggingFiner()) {
LOG.finer("... but we already have a better one.");
}
}
}
}
LOG.incrementProcessed(iprogress);
}
}
LOG.ensureCompleted(iprogress);
return (C != null) ? makeCluster(relation, C, D) : null;
}